The security of machine learning

Authors:
Marco Barreno;Blaine Nelson;Anthony D. Joseph;J. D. Tygar
Affiliations:
Computer Science Division, University of California, Berkeley, USA 94720-1776;Computer Science Division, University of California, Berkeley, USA 94720-1776;Computer Science Division, University of California, Berkeley, USA 94720-1776;Computer Science Division, University of California, Berkeley, USA 94720-1776
Venue:
Machine Learning
Year:
2010

Citing 0
Cited 12

Machine learning in adversarial environments

Machine Learning
Classifier evasion: models and open problems

PSDML'10 Proceedings of the international ECML/PKDD conference on Privacy and security issues in data mining and machine learning
A unifying view on dataset shift in classification

Pattern Recognition
Bagging classifiers for fighting poisoning attacks in adversarial classification tasks

MCS'11 Proceedings of the 10th international conference on Multiple classifier systems
Understanding the risk factors of learning in adversarial environments

Proceedings of the 4th ACM workshop on Security and artificial intelligence
Static detection of malicious JavaScript-bearing PDF documents

Proceedings of the 27th Annual Computer Security Applications Conference
Bio-inspired enhancement of reputation systems for intelligent environments

Information Sciences: an International Journal
Sampling attack against active learning in adversarial environment

MDAI'12 Proceedings of the 9th international conference on Modeling Decisions for Artificial Intelligence
Adversarial attacks against intrusion detection systems: Taxonomy, solutions and open issues

Information Sciences: an International Journal
An agent-based model to simulate and analyse behaviour under noisy and deceptive information

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Security analysis of online centroid anomaly detection

The Journal of Machine Learning Research
Neural network Trojan

Journal of Computer Security

Quantified Score

Hi-index	0.00

Visualization

Abstract

Machine learning's ability to rapidly evolve to changing and complex situations has helped it become a fundamental tool for computer security. That adaptability is also a vulnerability: attackers can exploit machine learning systems. We present a taxonomy identifying and analyzing attacks against machine learning systems. We show how these classes influence the costs for the attacker and defender, and we give a formal structure defining their interaction. We use our framework to survey and analyze the literature of attacks against machine learning systems. We also illustrate our taxonomy by showing how it can guide attacks against SpamBayes, a popular statistical spam filter. Finally, we discuss how our taxonomy suggests new lines of defenses.